Чем отличаются запросы с потоковой передачей и без неё при фильтрации контента?

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","model":"gpt-5.6-terra","choices":[{"delta":{},"finish_reason":"content_filter","index":0}],"usage":null}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","model":"gpt-5.6-terra","choices":[],"usage":{"prompt_tokens":27831,"completion_tokens":6966,"total_tokens":34797}}
data: [DONE]

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["APIYI_API_KEY"], base_url="https://api.apiyi.com/v1")

REFUSAL = "I'm sorry, but I cannot assist with that request."

def generate(messages, model="gpt-5.6-terra"):
    stream = client.chat.completions.create(
        model=model,
        messages=messages,
        stream=True,
        stream_options={"include_usage": True},
    )
    parts, finish = [], None
    for chunk in stream:
        if not chunk.choices:
            continue
        choice = chunk.choices[0]
        if choice.delta and choice.delta.content:
            parts.append(choice.delta.content)
            print(choice.delta.content, end="", flush=True)
        if choice.finish_reason:
            finish = choice.finish_reason

    text = "".join(parts)
    if finish != "content_filter":
        return text

    # Filtered: strip the trailing refusal and retry without streaming so the platform can switch routes
    partial = text.removesuffix(REFUSAL)
    print(f"\n[Cut off by content filter after {len(partial)} characters; retrying without streaming]")
    resp = client.chat.completions.create(model=model, messages=messages, timeout=600)
    return resp.choices[0].message.content